{"id":"W3199989184","doi":"10.1007/978-3-030-86365-4_34","title":"FMSNet: Underwater Image Restoration by Learning from a Synthesized Dataset","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Underwater; Computer science; Convolutional neural network; Artificial intelligence; Image restoration; Process (computing); Feature (linguistics); Image (mathematics); Artificial neural network; Pattern recognition (psychology); Decomposition; Image processing; Computer vision","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008481172,0.0005817518,0.0005677607,0.0004660753,0.0003021541,0.001453871,0.00318477,0.0003244019,0.0001904023],"category_scores_gemma":[0.0001485406,0.0005652377,0.00009476266,0.0003886913,0.0005092581,0.001523209,0.001951633,0.001067086,0.0001246277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004055289,"about_ca_system_score_gemma":0.0003951078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001319543,"about_ca_topic_score_gemma":0.0000845479,"domain_scores_codex":[0.9955399,0.0001285044,0.0005696001,0.001992098,0.001133551,0.000636368],"domain_scores_gemma":[0.996953,0.0005477452,0.0003567713,0.00179785,0.0002120619,0.0001326475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002661765,0.0001325836,0.00002738115,0.00008466565,0.00006819325,0.0007442363,0.001450495,0.003083606,0.1204534,0.005037968,0.009731904,0.859159],"study_design_scores_gemma":[0.0006987095,0.0003456378,0.0000296215,0.001182698,0.00003776915,0.00005295822,7.898192e-7,0.4672992,0.3554586,0.113558,0.05885611,0.002479804],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003144365,0.0005329673,0.9959146,0.0009353925,0.0006671794,0.0003475979,0.00008625368,0.0003734943,0.001111077],"genre_scores_gemma":[0.01886744,0.0001354048,0.9762717,0.002091767,0.0003999291,0.00002820168,0.001176406,0.00006978809,0.0009593167],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8566791,"threshold_uncertainty_score":0.9996799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01640619593191925,"score_gpt":0.2518439014843075,"score_spread":0.2354377055523883,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}